Title: PCA-PAG: a dual-channel patent abstract generation method based on cross-modal prefixes and cross-attention

Authors: Wei Zhu; Na Deng; Xu Chen; Yaoyi Jiao

Addresses: Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network, Hubei Provincial Engineering Research Center for Digital and Intelligent Manufacturing Technologies and Applications, School of Computer Science and Artificial Intelligence, Hubei University of Technology, Wuhan, Hubei, China ' Hubei Provincial Key Laboratory of Green Intelligent Computing Power Network, Hubei Provincial Engineering Research Center for Digital and Intelligent Manufacturing Technologies and Applications, School of Computer Science and Artificial Intelligence, Hubei University of Technology, Wuhan, Hubei, China ' School of Information Engineering, Zhongnan University of Economics and Law, Wuhan, Hubei, China ' Hubei Siji Technology Company Limited, Wuhan, Hubei, China

Abstract: With the increasing demand for automation in the patent domain, generating Chinese patent abstracts faces challenges such as weak alignment between patent figures and claims, as well as insufficient consistency in domain-specific terminology. This study proposes a cross-modal dual-channel fusion method for patent abstract generation, aimed at enhancing the accuracy of text-image understanding and abstract generation, thereby advancing patent automation technologies. This paper introduces a patent abstract automatic generation model, PCA-PAG, which features a dual-channel cross-modal fusion method. By extracting visual representations with a frozen BLIP-2 encoder, mapping the global visual vector into learnable visual prefixes, and incorporating text-vision cross-attention, the method achieves both global semantic guidance and fine-grained component alignment. It uses conditional cross-entropy and penalty mechanisms to optimise generation quality and is validated through various evaluation metrics. Compared with the strongest baseline, PCA-PAG improves BERT-F1 by 3.22 percentage points while maintaining a favourable performance-efficiency trade-off. It confirms that the dual-channel strategy offers a feasible and practically promising technological pathway for patent cross-modal abstract generation without significantly increasing inference costs.

Keywords: patent abstract generation; Chinese patents; dual channel fusion; cross modal prefixes; cross attention; text image alignment.

DOI: 10.1504/IJWGS.2026.154468

International Journal of Web and Grid Services, 2026 Vol.22 No.2, pp.201 - 224

Received: 19 Jan 2026
Accepted: 12 Mar 2026
Published online: 29 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article